Systems and methods are configured to perform prioritized processing of a plurality of processing objects under a time constraint. In various embodiments, a priority policy that includes deterministic prioritization rules, probabilistic prioritization rules, and a priority determination machine learning model is applied to the objects to determine high and low priority subsets. Here, the subsets are determined using the deterministic prioritization rules and a probabilistic ordering of the low priority subset is determined using the probabilistic prioritization rules and the priority determination machine learning model. In particular embodiments, the ordering is accomplished by determining a hybrid priority score for each object in the low priority subset based on a rule-based priority score and a machine-learning-based priority score. An investigatory subset is then composed of the high priority subset and objects from the low priority subset added until a termination time according to a data processing model and the probabilistic ordering.
Legal claims defining the scope of protection, as filed with the USPTO.
2. The computer-implemented method of claim 1, wherein the high priority subset comprises each of the processing objects of the plurality of processing objects that satisfies at least one of the one or more deterministic prioritization rules and the low priority subset comprises each of the processing objects of the plurality of processing objects that fails to satisfy any of the one or more deterministic prioritization rules.
4. The computer-implemented method of claim 3, wherein each of the probabilistic weight values is based on a past investigatory success measure for the corresponding probabilistic prioritization rule.
5. The computer-implemented method of claim 3, wherein the hybrid priority score for the processing object is further based on a valuation magnitude for the processing object.
7. The computer-implemented method of claim 1, wherein each of the plurality of processing objects describes an examinable claim and the data processing model comprises an overpaid claim detection model.
10. The apparatus of claim 9, wherein the high priority subset comprises each of the processing objects of the plurality of processing objects that satisfies at least one of the one or more deterministic prioritization rules and the low priority subset comprises each of the processing objects of the plurality of processing objects that fails to satisfy any of the one or more deterministic prioritization rules.
12. The apparatus of claim 11, wherein each of the probabilistic weight values is based on a past investigatory success measure for the corresponding probabilistic prioritization rule.
13. The apparatus of claim 11, wherein the hybrid priority score for the processing object is further based on a valuation magnitude for the processing object.
15. The apparatus of claim 9, wherein each of the plurality of processing objects describes an examinable claim and the data processing model comprises an overpaid claim detection model.
18. The non-transitory computer storage medium of claim 17, wherein the high priority subset comprises each of the processing objects of the plurality of processing objects that satisfies at least one of the one or more deterministic prioritization rules and the low priority subset comprises each of the processing objects of the plurality of processing objects that fails to satisfy any of the one or more deterministic prioritization rules.
20. The non-transitory computer storage medium of claim 19, wherein each of the probabilistic weight values is based on a past investigatory success measure for the corresponding probabilistic prioritization rule.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
June 12, 2020
September 20, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.